Deep Learning
- Michael Chang, Tomer Ullman, Antonio Torralba, Joshua B. Tenenbaum:
A Compositional Object-Based Approach To Learning Physical Dynamics (web) (bibtex)
Proceedings of the 5th International Conference on Learning Representations
#intuitive physics, #simulation, #deep learning, #unsupervised learning, #scene understanding
@article{MichaelChang:2017:07f51,
author = {Michael Chang and Tomer Ullman and Antonio Torralba and Joshua B. Tenenbaum},
journal = {Proceedings of the 5th International Conference on Learning Representations},
title = {A Compositional Object-Based Approach To Learning Physical Dynamics},
year = {2017},
keywords = {intuitive physics, simulation, deep learning, unsupervised learning, scene understanding},
doi = {},
url = {https://arxiv.org/abs/1612.00341}
}
- Renqiao Zhang, Jiajun Wu, Chengkai Zhang, William T. Freeman, Joshua B. Tenenbaum:
A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding (web) (bibtex)
Proceedings of the 38th Annual Conference of the Cognitive Science Society
#intuitive physics, #simulation, #deep learning, #scene understanding
@article{RenqiaoZhang:2016:84ee7,
author = {Renqiao Zhang and Jiajun Wu and Chengkai Zhang and William T. Freeman and Joshua B. Tenenbaum},
journal = {Proceedings of the 38th Annual Conference of the Cognitive Science Society},
title = {A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding},
year = {2016},
keywords = {intuitive physics, simulation, deep learning, scene understanding},
doi = {},
url = {http://blocks.csail.mit.edu/}
}
- Jiajun Wu, Joseph J. Lim, Hongyi Zhang, Joshua B. Tenenbaum, William T. Freeman:
Physics 101: Learning Physical Object Properties from Unlabeled Videos (web) (bibtex)
British Machine Vision Conference (BMVC)
#intuitive physics, #unsupervised learning, #deep learning, #scene understanding
@article{JiajunWu:2016:9e6c9,
author = {Jiajun Wu and Joseph J. Lim and Hongyi Zhang and Joshua B. Tenenbaum and William T. Freeman},
journal = {British Machine Vision Conference (BMVC)},
title = {Physics 101: Learning Physical Object Properties from Unlabeled Videos},
year = {2016},
keywords = {intuitive physics, unsupervised learning, deep learning, scene understanding},
doi = {},
url = {http://phys101.csail.mit.edu/}
}
- Jiajun Wu, Ilker Yildirim, Joseph J. Lim, William T. Freeman, Joshua B. Tenenbaum:
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#intuitive physics, #simulation, #deep learning, #unsupervised learning, #scene understanding
@article{JiajunWu:2015:27dc4,
author = {Jiajun Wu and Ilker Yildirim and Joseph J. Lim and William T. Freeman and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning},
year = {2015},
keywords = {intuitive physics, simulation, deep learning, unsupervised learning, scene understanding},
doi = {},
url = {http://galileo.csail.mit.edu/}
}
- Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman:
Single Image 3D Interpreter Network (web) (bibtex)
European Conference in Computer Vision (ECCV)
#deep learning, #self-supervised learning, #3d vision
@article{JiajunWu:2016:770f7,
author = {Jiajun Wu and Tianfan Xue and Joseph J. Lim and Yuandong Tian and Joshua B. Tenenbaum and Antonio Torralba and William T. Freeman},
journal = {European Conference in Computer Vision (ECCV)},
title = {Single Image 3D Interpreter Network},
year = {2016},
keywords = {deep learning, self-supervised learning, 3d vision},
doi = {},
url = {http://3dinterpreter.csail.mit.edu/}
}
- Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, Joshua B. Tenenbaum:
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#simulation, #deep learning, #generative adversarial learning, #3d vision
@article{JiajunWu:2016:3471d,
author = {Jiajun Wu and Chengkai Zhang and Tianfan Xue and William T. Freeman and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling},
year = {2016},
keywords = {simulation, deep learning, generative adversarial learning, 3d vision},
doi = {},
url = {http://3dgan.csail.mit.edu/}
}
- Zhoutong Zhang, Jiajun Wu, Qiujia Li, Zhengjia Huang, James Traer, Josh H. McDermott, Joshua B. Tenenbaum, William T. Freeman:
Generative Modeling of Audible Shapes for Object Perception (pdf) (bibtex)
IEEE International Conference on Computer Vision (ICCV)
#deep learning, #simulation, #auditory perception, #scene understanding
@article{ZhoutongZhang:2017:4f1fd,
author = {Zhoutong Zhang and Jiajun Wu and Qiujia Li and Zhengjia Huang and James Traer and Josh H. McDermott and Joshua B. Tenenbaum and William T. Freeman},
journal = {IEEE International Conference on Computer Vision (ICCV)},
title = {Generative Modeling of Audible Shapes for Object Perception},
year = {2017},
keywords = {deep learning, simulation, auditory perception, scene understanding},
doi = {},
url = {https://jiajunwu.com/papers/gensound_iccv.pdf}
}
- Jiajun Wu, Joshua B. Tenenbaum, Pushmeet Kohli:
Neural Scene De-rendering (web) (bibtex)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
#deep learning, #self-supervised learning, #inverse graphics, #computer vision, #scene understanding
@article{JiajunWu:2017:2afa9,
author = {Jiajun Wu and Joshua B. Tenenbaum and Pushmeet Kohli},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {Neural Scene De-rendering},
year = {2017},
keywords = {deep learning, self-supervised learning, inverse graphics, computer vision, scene understanding},
doi = {},
url = {http://nsd.csail.mit.edu/}
}
- Jiajun Wu, Erika Lu, Pushmeet Kohli, William T. Freeman, Joshua B. Tenenbaum:
Learning to See Physics via Visual De-animation (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#intuitive physics, #simulation, #deep learning, #scene understanding
@article{JiajunWu:2017:4849f,
author = {Jiajun Wu and Erika Lu and Pushmeet Kohli and William T. Freeman and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Learning to See Physics via Visual De-animation},
year = {2017},
keywords = {intuitive physics, simulation, deep learning, scene understanding},
doi = {},
url = {http://vda.csail.mit.edu/}
}
- Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, William T. Freeman, Joshua B. Tenenbaum:
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#3d vision, #deep learning
@article{JiajunWu:2017:cfe2b,
author = {Jiajun Wu and Yifan Wang and Tianfan Xue and Xingyuan Sun and William T. Freeman and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {MarrNet: 3D Shape Reconstruction via 2.5D Sketches},
year = {2017},
keywords = {3d vision, deep learning},
doi = {},
url = {http://marrnet.csail.mit.edu/}
}
- Michael Janner, Jiajun Wu, Tejas D. Kulkarni, Ilker Yildirim, Joshua B. Tenenbaum:
Self-Supervised Intrinsic Image Decomposition (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#computer vision, #deep learning, #self-supervised learning
@article{MichaelJanner:2017:e02af,
author = {Michael Janner and Jiajun Wu and Tejas D. Kulkarni and Ilker Yildirim and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Self-Supervised Intrinsic Image Decomposition},
year = {2017},
keywords = {computer vision, deep learning, self-supervised learning},
doi = {},
url = {http://rin.csail.mit.edu/}
}
- Zhoutong Zhang, Qiujia Li, Zhengjia Huang, Jiajun Wu, Joshua B. Tenenbaum, William T. Freeman:
Shape and Material from Sound (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#auditory perception, #deep learning, #simulation
@article{ZhoutongZhang:2017:1d3c7,
author = {Zhoutong Zhang and Qiujia Li and Zhengjia Huang and Jiajun Wu and Joshua B. Tenenbaum and William T. Freeman},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Shape and Material from Sound},
year = {2017},
keywords = {auditory perception, deep learning, simulation},
doi = {},
url = {http://sound.csail.mit.edu/}
}
- Tejas D Kulkarni, Karthik Narasimhan, Ardavan Saeedi, Josh Tenenbaum:
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#reinforcement learning, #hierarchical modeling, #deep learning
@article{TejasDKulkarni:2016:847fe,
author = {Tejas D Kulkarni and Karthik Narasimhan and Ardavan Saeedi and Josh Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation},
year = {2016},
keywords = {reinforcement learning, hierarchical modeling, deep learning},
doi = {},
url = {http://papers.nips.cc/paper/6232-hierarchical-deep-reinforcement-learning-integrating-temporal-abstraction-and-intrinsic-motivation}
}
- Tejas D Kulkarni, William F Whitney, Pushmeet Kohli, Josh Tenenbaum:
Deep Convolutional Inverse Graphics Network (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#inverse vision, #deep learning, #disentangled representation,
@article{TejasDKulkarni:2015:19456,
author = {Tejas D Kulkarni and William F Whitney and Pushmeet Kohli and Josh Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Deep Convolutional Inverse Graphics Network},
year = {2015},
keywords = {inverse vision, deep learning, disentangled representation,},
doi = {},
url = {http://papers.nips.cc/paper/5851-deep-convolutional-inverse-graphics-network}
}
- Tejas D Kulkarni, Pushmeet Kohli, Joshua B Tenenbaum, Vikash Mansinghka:
Picture : A Probabilistic Programming Language for Scene Perception (pdf) (doi) (bibtex)
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
#analysis-by-synthesis, #inference, #deep learning, #inverse vision, #3d vision, #probabilistic programming
@article{TejasDKulkarni:2015:cf27d,
author = {Tejas D Kulkarni and Pushmeet Kohli and Joshua B Tenenbaum and Vikash Mansinghka},
journal = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
title = {Picture : A Probabilistic Programming Language for Scene Perception},
year = {2015},
keywords = {analysis-by-synthesis, inference, deep learning, inverse vision, 3d vision, probabilistic programming},
doi = {10.1109/CVPR.2015.7299068},
url = {http://openaccess.thecvf.com/content_cvpr_2015/papers/Kulkarni_Picture_A_Probabilistic_2015_CVPR_paper.pdf}
}
- Xingyuan Sun, Jiajun Wu, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Tianfan Xue, Joshua B. Tenenbaum, William T. Freeman:
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (web) (bibtex)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
#3d vision, #deep learning
@article{XingyuanSun:2018:02ad6,
author = {Xingyuan Sun and Jiajun Wu and Xiuming Zhang and Zhoutong Zhang and Chengkai Zhang and Tianfan Xue and Joshua B. Tenenbaum and William T. Freeman},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling},
year = {2018},
keywords = {3d vision, deep learning},
doi = {},
url = {http://pix3d.csail.mit.edu}
}
- Shaoxiong Wang, Jiajun Wu, Xingyuan Sun, Wenzhen Yuan, William T. Freeman, Joshua B. Tenenbaum, Edward H. Adelson:
3D Shape Perception from Monocular Vision, Touch, and Shape Priors (web) (bibtex)
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
#3d vision, #multi-modal learning, #deep learning
@article{ShaoxiongWang:2018:158c4,
author = {Shaoxiong Wang and Jiajun Wu and Xingyuan Sun and Wenzhen Yuan and William T. Freeman and Joshua B. Tenenbaum and Edward H. Adelson},
journal = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
title = {3D Shape Perception from Monocular Vision, Touch, and Shape Priors},
year = {2018},
keywords = {3d vision, multi-modal learning, deep learning},
doi = {},
url = {http://touch.csail.mit.edu}
}
- Anurag Ajay, Jiajun Wu, Nima Fazeli, Maria Bauza, Leslie P. Kaelbling, Joshua B. Tenenbaum, Alberto Rodriguez:
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing (web) (bibtex)
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
#dynamics modeling, #deep learning, #robotics
@article{AnuragAjay:2018:2ddc2,
author = {Anurag Ajay and Jiajun Wu and Nima Fazeli and Maria Bauza and Leslie P. Kaelbling and Joshua B. Tenenbaum and Alberto Rodriguez},
journal = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
title = {Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing},
year = {2018},
keywords = {dynamics modeling, deep learning, robotics},
doi = {},
url = {http://physplus.csail.mit.edu}
}
- Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum:
Learning Shape Priors for Single-View 3D Completion and Reconstruction (web) (bibtex)
European Conference on Computer Vision (ECCV)
#3d vision, #deep learning
@article{JiajunWu:2018:11782,
author = {Jiajun Wu and Chengkai Zhang and Xiuming Zhang and Zhoutong Zhang and William T. Freeman and Joshua B. Tenenbaum},
journal = {European Conference on Computer Vision (ECCV)},
title = {Learning Shape Priors for Single-View 3D Completion and Reconstruction},
year = {2018},
keywords = {3d vision, deep learning},
doi = {},
url = {http://shapehd.csail.mit.edu/}
}
- Zhijian Liu, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu:
Physical Primitive Decomposition (web) (bibtex)
European Conference on Computer Vision (ECCV)
#3d vision, #deep learning, #intuitive physics
@article{ZhijianLiu:2018:7414d,
author = {Zhijian Liu and William T. Freeman and Joshua B. Tenenbaum and Jiajun Wu},
journal = {European Conference on Computer Vision (ECCV)},
title = {Physical Primitive Decomposition},
year = {2018},
keywords = {3d vision, deep learning, intuitive physics},
doi = {},
url = {http://ppd.csail.mit.edu/}
}
- Shunyu Yao, Tzu-Ming Harry Hsu, Jun-Yan Zhu, Jiajun Wu, Antonio Torralba, William T. Freeman, Joshua B. Tenenbaum:
3D-Aware Scene Manipulation via Inverse Graphics (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#3d vision, #deep learning, #scene understanding
@article{ShunyuYao:2018:89f01,
author = {Shunyu Yao and Tzu-Ming Harry Hsu and Jun-Yan Zhu and Jiajun Wu and Antonio Torralba and William T. Freeman and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {3D-Aware Scene Manipulation via Inverse Graphics},
year = {2018},
keywords = {3d vision, deep learning, scene understanding},
doi = {},
url = {}
}
- Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, Joshua B. Tenenbaum:
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (web) (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#visual reasoning, #deep learning, #scene understanding
@article{KexinYi:2018:480b1,
author = {Kexin Yi and Jiajun Wu and Chuang Gan and Antonio Torralba and Pushmeet Kohli and Joshua B. Tenenbaum},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding},
year = {2018},
keywords = {visual reasoning, deep learning, scene understanding},
doi = {},
url = {http://nsvqa.csail.mit.edu/}
}
- Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu:
Learning to Reconstruct Shapes from Unseen Categories (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#3d vision, #deep learning
@article{XiumingZhang:2018:596f7,
author = {Xiuming Zhang and Zhoutong Zhang and Chengkai Zhang and William T. Freeman and Joshua B. Tenenbaum and Jiajun Wu},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Learning to Reconstruct Shapes from Unseen Categories},
year = {2018},
keywords = {3d vision, deep learning},
doi = {},
url = {}
}
- Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu:
Learning to Exploit Stability for 3D Scene Parsing (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#3d vision, #deep learning, #scene understanding
@article{YilunDu:2018:dc7d0,
author = {Yilun Du and Zhijian Liu and Hector Basevi and Ales Leonardis and William T. Freeman and Joshua B. Tenenbaum and Jiajun Wu},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Learning to Exploit Stability for 3D Scene Parsing},
year = {2018},
keywords = {3d vision, deep learning, scene understanding},
doi = {},
url = {}
}
- Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Joshua B. Tenenbaum, William T. Freeman:
Visual Object Networks: Image Generation with Disentangled 3D Representations (bibtex)
Advances in Neural Information Processing Systems (NIPS)
#3d vision, #deep learning
@article{Jun-YanZhu:2018:3ee07,
author = {Jun-Yan Zhu and Zhoutong Zhang and Chengkai Zhang and Jiajun Wu and Antonio Torralba and Joshua B. Tenenbaum and William T. Freeman},
journal = {Advances in Neural Information Processing Systems (NIPS)},
title = {Visual Object Networks: Image Generation with Disentangled 3D Representations},
year = {2018},
keywords = {3d vision, deep learning},
doi = {},
url = {}
}
- Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman:
3D Interpreter Networks for Viewer-Centered Wireframe Modeling (web) (bibtex)
International Journal of Computer Vision (IJCV)
#3d vision, #deep learning
@article{JiajunWu:2018:ad749,
author = {Jiajun Wu and Tianfan Xue and Joseph J. Lim and Yuandong Tian and Joshua B. Tenenbaum and Antonio Torralba and William T. Freeman},
journal = {International Journal of Computer Vision (IJCV)},
title = {3D Interpreter Networks for Viewer-Centered Wireframe Modeling},
year = {2018},
keywords = {3d vision, deep learning},
doi = {},
url = {http://3dinterpreter.csail.mit.edu/}
}
- Ilker Yildirim, Kevin Smith, Mario Belledonne, Jiajun Wu, Joshua B. Tenenbaum:
Neurocomputational Modeling of Human Physical Scene Understanding (pdf) (bibtex)
Conference on Cognitive Computational Neuroscience (CCN)
#intuitive physics, #deep learning, #scene understanding
@article{IlkerYildirim:2018:068cb,
author = {Ilker Yildirim and Kevin Smith and Mario Belledonne and Jiajun Wu and Joshua B. Tenenbaum},
journal = {Conference on Cognitive Computational Neuroscience (CCN)},
title = {Neurocomputational Modeling of Human Physical Scene Understanding},
year = {2018},
keywords = {intuitive physics, deep learning, scene understanding},
doi = {},
url = {https://jiajunwu.com/papers/humanphys_ccn.pdf}
}
- Amir Arsalan Soltani, Haibin Huang, Jiajun Wu, Tejas D Kulkarni, Joshua B Tenenbaum:
Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes with Deep Generative (web) (doi) (bibtex)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
#2d to 3d, #3d vision, #3d generation, #3d reconstruction, #inverse vision, #scene understanding, #deep learning
@article{AmirArsalanSoltani:2017:4a1d2,
author = {Amir Arsalan Soltani and Haibin Huang and Jiajun Wu and Tejas D Kulkarni and Joshua B Tenenbaum},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes with Deep Generative },
year = {2017},
keywords = {2d to 3d, 3d vision, 3d generation, 3d reconstruction, inverse vision, scene understanding, deep learning},
doi = {10.1109/CVPR.2017.269},
url = {https://github.com/Amir-Arsalan/Synthesize3DviaDepthOrSil}
}
add/edit publications
